Cataracts are one of the leading causes of vision impairment globally, characterized by lens clouding, which can result in blurred vision, faded colors, and halos around lights. This condition affects over 2.2 billion people worldwide, yet diagnosing cataracts often requires time-consuming and costly consultations with healthcare professionals. To address this issue, we developed a cross-platform mobile application designed to facilitate the detection of cataracts using machine learning techniques. Specifically, we implemented Support Vector Machine (SVM) classifiers with three different kernel functions: Linear, Polynomial, and Radial Basis Function (RBF). Through our experiments, we found that the RBF kernel provided the best performance, achieving an accuracy of approximately 95%. The application leverages image processing and classification algorithms to efficiently assess the presence of cataracts, making it accessible to users without the need for professional intervention. Our results, validated through classification reports and accuracy metrics, demonstrate the potential of this mobile solution to improve early diagnosis and accessibility of cataract detection. This study contributes to ongoing efforts to harness technology for medical image analysis and highlights the importance of selecting appropriate machine learning models for effective healthcare solutions.